© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4023
    Prev
    Next
    INDEX
    Explanations

    code-related terms, especially potentially Javascript/web related code

    oai_token-act-pair · gemini-2.0-flash

    code snippets and docs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     decorativas
    -0.60
    Baik
    -0.59
    pozdrawiam
    -0.58
    Literatuur
    -0.57
     navideñas
    -0.56
     Inscrivez
    -0.55
     ""))
    -0.55
     culturales
    -0.54
     sexuales
    -0.53
    Semoga
    -0.53
    POSITIVE LOGITS
    MigrationBuilder
    0.61
    ########.
    0.60
    }{*}{}
    0.56
     samarbeid
    0.54
     ujednoznacz
    0.53
     CreateTagHelper
    0.53
     samfun
    0.52
    sizeCache
    0.50
    ividual
    0.50
     forskjellige
    0.50
    Activations Density 0.914%

    No Known Activations